i wanted to implement incremental PCA. Got this code for stack overflow but i am wondering what y = chunk.pop("y") does and what is this argument "y" to pop from sklearn.decomposition import IncrementalPCA import csv import sys import numpy as np import pandas as pd
dataset = sys.argv[1] chunksize_ = 5 * 25000 dimensions = 300 reader = pd.read_csv(dataset, sep = ',', chunksize = chunksize_) sklearn_pca = IncrementalPCA(n_components=dimensions) for chunk in reader: y = chunk.pop("Y") sklearn_pca.partial_fit(chunk) # Computed mean per feature mean = sklearn_pca.mean_ # and stddev stddev = np.sqrt(sklearn_pca.var_) Xtransformed = None for chunk in pd.read_csv(dataset, sep = ',', chunksize = chunksize_): y = chunk.pop("Y") Xchunk = sklearn_pca.transform(chunk) if Xtransformed == None: Xtransformed = Xchunk else: Xtransformed = np.vstack((Xtransformed, Xchunk)) -- https://mail.python.org/mailman/listinfo/python-list